INDEX

Explanations

terminology related to medical conditions and processes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Bronnen

-0.71

ɫ

-0.66

 Saltar

-0.66

uric

-0.66

 nią

-0.65

[]

-0.65

 Cath

-0.64

Efq

-0.64

"])

-0.62

POSITIVE LOGITS

 Tapatalk

0.63

>{@

0.57

 onPostExecute

0.56

 which

0.53

 newOwner

0.50

RefNanny

0.50

 gevolg

0.49

webElement

0.47

 instead

0.47

hoodie

0.46

Activations Density 1.609%

terminology related to medical conditions and processes

No Comments

No Known Activations